RLTasksby ulam.ai
Models / Anthropic

Anthropic / MODEL EVIDENCE

Claude 3.5 Sonnet (Jun 2024)

13 benchmarks · 14 observations · 13 sources · released 2024-06-20

Scores at a glance

13 benchmarks · large dot: Claude 3.5 Sonnet (Jun 2024); small dots: closest models where reported

GPQA Diamond ↗54.04%
9.2896.4

Claude 3.5 Sonnet (Jun 2024) · GPQA diamond · Best score (across scorers) · % ↗

MATH Level 5 ↗51.68%
3.2998.13

Claude 3.5 Sonnet (Jun 2024) · MATH level 5 · Best score (across scorers) · % ↗

Cybench ↗17.5%
555

Claude 3.5 Sonnet (Jun 2024) · Cybench · Unguided % Solved · % ↗

MMLU ↗86.5%
29.587.3

Claude 3.5 Sonnet (Jun 2024) · MMLU · EM · % ↗

SimpleBench ↗27.5%
10.781.9

Claude 3.5 Sonnet (Jun 2024) · SimpleBench · Score (AVG@5) · % ↗

VPCT ↗33%
3091

Claude 3.5 Sonnet (Jun 2024) · VPCT · Correct · % ↗

DTBench ↗67.77%
41.6598.93

Claude 3.5 Sonnet (Jun 2024) · DTBench · Accuracy · % ↗

Video-MME ↗60%
37.975

Claude 3.5 Sonnet (Jun 2024) · VideoMME · Overall (no subtitles) · % ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  2. Holistic Evaluation of Language Models (HELM) ↗

    Stanford Center for Research on Foundation Models

  3. Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models ↗

    Zhang, Andy K., Perry, Neil, Dulepet, Riya, Ji, Joey, Menders, Celeste, Lin, Justin W. et al. · 2024

    All 27 authors

    Zhang, Andy K., Perry, Neil, Dulepet, Riya, Ji, Joey, Menders, Celeste, Lin, Justin W., Jones, Eliot, Hussein, Gashon, Liu, Samantha, Jasper, Donovan, Peetathawatchai, Pura, Glenn, Ari, Sivashankar, Vikram, Zamoshchin, Daniel, Glikbarg, Leo, Askaryar, Derek, Yang, Mike, Zhang, Teddy, Alluri, Rishi, Tran, Nathan, Sangpisit, Rinnara, Yiorkadjis, Polycarpos, Osele, Kenny, Raghupathi, Gautham, Boneh, Dan, Ho, Daniel E., Liang, Percy

  4. FrontierMath Tier 4 (v1, old) ↗

    Epoch AI

  5. FrontierMath Tiers 1-3 (v1, old) ↗

    Epoch AI

  6. GPQA Diamond ↗

    Epoch AI

  7. MATH Level 5 ↗

    Epoch AI

  8. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  9. SimpleBench ↗

    Epoch AI

  10. Capabilities & benchmarking — retained external evaluation records ↗

    Epoch AI · 2026

  11. WeirdML ↗

    Håvard Tveit Ihle

  12. Measuring AI Ability to Complete Long Software Tasks ↗

    METR

  13. Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis ↗

    Fu, Chaoyou, Dai, Yuhan, Luo, Yongdong, Li, Lei, Ren, Shuhuai, Zhang, Renrui et al. · 2024

    All 21 authors

    Fu, Chaoyou, Dai, Yuhan, Luo, Yongdong, Li, Lei, Ren, Shuhuai, Zhang, Renrui, Wang, Zihan, Zhou, Chenyu, Shen, Yunhang, Zhang, Mengdan, Chen, Peixian, Li, Yanwei, Lin, Shaohui, Zhao, Sirui, Li, Ke, Xu, Tong, Zheng, Xiawu, Chen, Enhong, Shan, Caifeng, He, Ran, Sun, Xing

Names used in source tables

Claude 3.5 Sonnet (Jun 2024)